Imperial College London

DrKonstantinNikolic

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Visiting Professor
 
 
 
//

Contact

 

+44 (0)20 7594 1594k.nikolic

 
 
//

Location

 

Bessemer 420CBessemer BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Cheng:2020:10.3390/asi3020028,
author = {Cheng, R and Mirza, KB and Nikolic, K},
doi = {10.3390/asi3020028},
journal = {Applied System Innovation},
pages = {1--16},
title = {Neuromorphic robotic platform with visual input, processor and actuator, based on spiking neural networks},
url = {http://dx.doi.org/10.3390/asi3020028},
volume = {3},
year = {2020}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - This paper describes the design and modus of operation of a neuromorphic robotic platform based on SpiNNaker, and its implementation on the goalkeeper task. The robotic system utilises an address event representation (AER) type of camera (dynamic vision sensor (DVS)) to capture features of a moving ball, and a servo motor to position the goalkeeper to intercept the incoming ball. At the backbone of the system is a microcontroller (Arduino Due) which facilitates communication and control between different robot parts. A spiking neuronal network (SNN), which is running on SpiNNaker, predicts the location of arrival of the moving ball and decides where to place the goalkeeper. In our setup, the maximum data transmission speed of the closed-loop system is approximately 3000 packets per second for both uplink and downlink, and the robot can intercept balls whose speed is up to 1 m/s starting from the distance of about 0.8 m. The interception accuracy is up to 85%, the response latency is 6.5 ms and the maximum power consumption is 7.15 W. This is better than previous implementations based on PC. Here, a simplified version of an SNN has been developed for the ‘interception of a moving object’ task, for the purpose of demonstrating the platform, however a generalised SNN for this problem is a nontrivial problem. A demo video of the robot goalie is available on YouTube.
AU - Cheng,R
AU - Mirza,KB
AU - Nikolic,K
DO - 10.3390/asi3020028
EP - 16
PY - 2020///
SN - 2571-5577
SP - 1
TI - Neuromorphic robotic platform with visual input, processor and actuator, based on spiking neural networks
T2 - Applied System Innovation
UR - http://dx.doi.org/10.3390/asi3020028
UR - https://www.mdpi.com/2571-5577/3/2/28
UR - http://hdl.handle.net/10044/1/80253
VL - 3
ER -